Fiction Eval leaderboard · model review

Mistral Large for fiction writing — blind-judged review

July 2026: 10 fresh genre scenes, three tries each, judged blind against 7 other frontier models by a different AI family.

Where it lands

#7 of 8 — score 1118 (likely 1054–1167), record 35–162–10 across 207 blind matchups. Slop 17.79 per 1,000 words (5th-cleanest of the field — a separate AI-tell count, not the quality ranking).

#	Model	Score	Record	Slop
1	Claude Opus 4.8	1927 (likely 1888–1976)	150–14–43	14.88
2	Claude Sonnet 4.6	1914 (likely 1874–1961)	146–15–46	18.57
3	Grok 4.3	1856 (likely 1815–1899)	137–28–42	9.43
4	GLM 5.2	1776 (likely 1732–1822)	117–42–42	17.53
5	Gemini 3.1 Pro	1471 (likely 1423–1519)	78–104–13	13.45
6	DeepSeek V3.2	1251 (likely 1201–1302)	52–144–11	23.24
7	Mistral Large	1118 (likely 1054–1167)	35–162–10	17.79
8	Llama 4 Maverick	686 (likely 627–741)	0–206–1	22.92

Judged strengths and weaknesses

Traits where Mistral Large scores above the field average: none. Below the field average: voice, pacing, dialogue, genre convention, avoiding AI tells. (Each rated 1–5 by the judge; field average taken across all eight models.)

Sample

LitRPG — “party aftermath” scene; full version on the board.

The screen flickered, a sickly pulse of red light bleeding through the black. My vision swam—no, not my vision. The *system* was resolving, pixel by pixel, like a wound stitching itself shut. **PARTY STATUS: WIPED** **DEATH PENALTY: HARDCORE MODE ENGAGED** The words hung there, jagged and final. I swallowed, but my throat was sand. My fingers twitched toward the log, but I already knew. I’d seen the numbers. Seen the health bars. **Lira (Rogue) – DECEASED** **Garrick (Tank) – DECEASED** **Vex (DPS) – DECEASED** **Kael (Healer) – SURVIVOR** Kael. That was me. The one left standing. The one who’d failed. A new notification blinked into existence, its edges sharp as broken glass. **ACCOUNT FLAGGED: PERMANENT DELETION** **USER: Garrick (Tank) – VIOLATION: TERMINAL DEBT** My breath hitched. *Terminal debt.* That wasn’t just gear loss. That wasn’t just a level drop. That was *gone.* No respawn. No appeal. No second chance. The system log scrolled, merciless: **Garrick has exceeded maximum allowed death penalties.** **Account purged. Character data erased.** **All assets liquidated to …

Head-to-heads

vs Claude Opus 4.8 · vs Claude Sonnet 4.6 · vs Grok 4.3 · vs GLM 5.2 · vs Gemini 3.1 Pro · vs DeepSeek V3.2 · vs Llama 4 Maverick

How it works: every pair of models is judged blind on the same scene, with the passages' order flipped so being shown first can't sway it, by GPT-5.4 — a family that isn't on the board, so nobody scores their own side. Each score carries a likely range; overlapping ranges are called a tie. Slop is scored separately by a fixed checklist, not an AI. Full board, every prompt, and the FAQ: thebookfactoryai.com/board. Get each new board by email on the model-drop list.

Writing a book of your own? Book Factory runs the same craft checks on full manuscripts.